Surely you’d need TTS for that one, too? Which one do you use, is it open weights?
Comment on AI chatbots unable to accurately summarise news, BBC finds
tal@lemmy.today 1 year ago
They are, however, able to inaccurately summarize it in GLaDOS’s voice, which is a point in their favor.
JackGreenEarth@lemm.ee 1 year ago
brucethemoose@lemmy.world 1 year ago
Zephyra just came out, seems sick:
There are also some “native” tts LLMs like GLM 9B, which “capture” more information in the output than pure text input.
ag10n@lemmy.world 1 year ago
A website with zero information, and barely anything on their huggingface page. What’s exciting about this?
brucethemoose@lemmy.world 1 year ago
Whoops, yeah, should have linked the blog.
I didn’t want to link the individual models because I’m not sure hybrid or pure transformers is better?
JohnEdwa@sopuli.xyz 1 year ago
Yeah, out of all the generative AI fields, voice generation at this point is like 95% there in its capability of producing convincing speech even with consumer level tech like ElevenLabs. That last 5% might not even be solvable currently, as it’s those moments it gets the feeling, intonation or pronunciation wrong when the only context you give it is a text input.
Especially voice cloning - the DRG Cortana Mission Control mod is one of the examples I like to use.